Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 7698
    Prev
    Next
    INDEX
    Explanations

    social media links and websites

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    640
    +0.13
    0.6%
    107
    +0.12
    0.5%
    102
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.13
    0.01
    313
    +0.12
    0.01
    500
    +0.12
    0.01
    Negative Logits
     lung
    -0.74
     cholesterol
    -0.73
     deposit
    -0.72
     deposits
    -0.72
     Pug
    -0.72
     Sinai
    -0.71
     deserts
    -0.70
     Pyramid
    -0.66
     consolid
    -0.66
     Lisbon
    -0.66
    POSITIVE LOGITS
    groups
    1.33
    events
    1.29
    pages
    1.25
    intent
    1.18
    hash
    1.15
    realDonaldTrump
    1.12
    search
    1.06
    photos
    1.04
    sports
    1.03
    user
    1.03
    Activations Density 0.012%

    No Known Activations